A measurement study of the ChatGPT plugin store found widespread manifest exposure, weak API authentication, and metadata inconsistencies, with some vulnerabilities reduced after reporting to OpenAI.
Multi-step jailbreaking privacy attacks on chatgpt,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Security study based on the Chatgptplugin system: ldentifying Security Vulnerabilities
A measurement study of the ChatGPT plugin store found widespread manifest exposure, weak API authentication, and metadata inconsistencies, with some vulnerabilities reduced after reporting to OpenAI.